Sung-Eui Yoon

Visual Place Recognition (VPR) is a task of estimating the location of a query image, predominantly executed through image retrieval using learned global descriptors from a reference database of geo-tagged images. While recent approaches have aimed to improve the scalability of VPR training by leveraging classification loss as a proxy task, this objective discretizes the feature space into distinct class regions, often overlooking visual differences between classes. This discretization makes VPR systems particularly vulnerable to extreme visual changes such as lifelong variations. To remedy these problems, we propose a novel Class-Relational Objective (CRO) that transforms one-hot labels into soft labels by considering visual information of inter-class relations. We further enhance this method by dynamically adjusting the influence of CRO based on class weight magnitudes, which serve as an indicator of class stability as supported by derivative analysis. Comprehensive experiments across diverse benchmarks, ranging from general visual variations to extreme lifelong changes, demonstrate that our method outperforms existing methods. The source code will be made publicly available.

Non-prehensile manipulation using onboard sensing presents a fundamental challenge: the manipulated object occludes the sensor's field of view, creating occluded regions that can lead to collisions. We propose CURA-PPO, a reinforcement learning framework that addresses this challenge by explicitly modeling uncertainty under partial observability. By predicting collision possibility as a distribution, we extract both risk and uncertainty to guide the robot's actions. The uncertainty term encourages active perception, enabling simultaneous manipulation and information gathering to resolve occlusions. When combined with confidence maps that capture observation reliability, our approach enables safe navigation despite severe sensor occlusion. Extensive experiments across varying object sizes and obstacle configurations demonstrate that CURA-PPO achieves up to 3X higher success rates than the baselines, with learned behaviors that handle occlusions. Our method provides a practical solution for autonomous manipulation in cluttered environments using only onboard sensing.